From 2d24b027c9c2d8d9c4adc9ea33af200e08ec8c63 Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 09:29:46 -0400 Subject: [PATCH 1/6] perf-test --- docs/docs/get-started/what-is-openrag.mdx | 38 ++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index bae90d26..ea907cb3 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -3,6 +3,9 @@ title: What is OpenRAG? slug: / --- +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform: @@ -83,4 +86,37 @@ The **OpenRAG Backend** is the central orchestration service that coordinates al **Third Party Services** like **Google Drive** connect to the **OpenRAG Backend** through OAuth authentication, allowing synchronication of cloud storage with the OpenSearch knowledge base. -The **OpenRAG Frontend** provides the user interface for interacting with the system. \ No newline at end of file +The **OpenRAG Frontend** provides the user interface for interacting with the system. + +## Performance expectations + +On a local VM with 7 vCPUs and 8 GiB RAM, OpenRAG ingested ~5.03 GB across 1,083 files in ~42 minutes, or ~2.4 documents per second. You can generally expect equal or better performance on developer laptops and significantly faster on servers. Throughput scales with CPU cores, memory, storage speed, and configuration choices such as embedding model, chunk size and overlap, and concurrency. + +The 12 errors (~1.1%) were file‑specific and did not stop the pipeline. + +Ingestion dataset: + +* Total files: 1,083 items mounted +* Total size on disk: 5,026,474,862 bytes (~5.03 GB) + +Hardware specifications: + +* Machine: Apple M4 Pro +* Podman VM: + * Name: `podman-machine-default` + * Type: `applehv` + * vCPUs: 7 + * Memory: 8 GiB + * Disk size: 100 GiB + +Test results: + +```text +2025-09-24T22:40:45.542190Z /app/src/main.py:231 Ingesting default documents when ready disable_langflow_ingest=False +2025-09-24T22:40:45.546385Z /app/src/main.py:270 Using Langflow ingestion pipeline for default documents file_count=1082 +... +2025-09-24T23:19:44.866365Z /app/src/main.py:351 Langflow ingestion completed success_count=1070 error_count=12 total_files=1082 +``` + +* Elapsed time: ~42 minutes 15 seconds (2,535 seconds) +* Throughput: ~2.4 documents/second \ No newline at end of file From b44d108efb7a780b5d6372a6055ba0ec08fe3691 Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 09:30:37 -0400 Subject: [PATCH 2/6] dont-need-tabs-import --- docs/docs/get-started/what-is-openrag.mdx | 3 --- 1 file changed, 3 deletions(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index ea907cb3..19f89ba3 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -3,9 +3,6 @@ title: What is OpenRAG? slug: / --- -import Tabs from '@theme/Tabs'; -import TabItem from '@theme/TabItem'; - OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform: From ac43159f18c668547c1148f15fcccb8c908c3347 Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 13:43:34 -0400 Subject: [PATCH 3/6] Apply suggestion from @aimurphy Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com> --- docs/docs/get-started/what-is-openrag.mdx | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index 19f89ba3..aec21cdb 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -87,7 +87,11 @@ The **OpenRAG Frontend** provides the user interface for interacting with the sy ## Performance expectations -On a local VM with 7 vCPUs and 8 GiB RAM, OpenRAG ingested ~5.03 GB across 1,083 files in ~42 minutes, or ~2.4 documents per second. You can generally expect equal or better performance on developer laptops and significantly faster on servers. Throughput scales with CPU cores, memory, storage speed, and configuration choices such as embedding model, chunk size and overlap, and concurrency. +On a local VM with 7 vCPUs and 8 GiB RAM, OpenRAG ingested approximately 5.03 GB across 1,083 files in about 42 minutes. +This equates to approximately 2.4 documents per second. + +You can generally expect equal or better performance on developer laptops and significantly faster on servers. +Throughput scales with CPU cores, memory, storage speed, and configuration choices such as embedding model, chunk size and overlap, and concurrency. The 12 errors (~1.1%) were file‑specific and did not stop the pipeline. From 036f62e99adb49720fd7f69b9f153ac87236004b Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 13:43:45 -0400 Subject: [PATCH 4/6] Apply suggestion from @aimurphy Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com> --- docs/docs/get-started/what-is-openrag.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index aec21cdb..e84e9fef 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -93,7 +93,8 @@ This equates to approximately 2.4 documents per second. You can generally expect equal or better performance on developer laptops and significantly faster on servers. Throughput scales with CPU cores, memory, storage speed, and configuration choices such as embedding model, chunk size and overlap, and concurrency. -The 12 errors (~1.1%) were file‑specific and did not stop the pipeline. +This test returned 12 errors (approximately 1.1%). +All errors were file‑specific, and they didn't stop the pipeline. Ingestion dataset: From 4a4fa7b843de569191f88d0bf12fcfcfa4a5304c Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 13:43:54 -0400 Subject: [PATCH 5/6] Apply suggestion from @aimurphy Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com> --- docs/docs/get-started/what-is-openrag.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index e84e9fef..6b6f71c8 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -99,7 +99,7 @@ All errors were file‑specific, and they didn't stop the pipeline. Ingestion dataset: * Total files: 1,083 items mounted -* Total size on disk: 5,026,474,862 bytes (~5.03 GB) +* Total size on disk: 5,026,474,862 bytes (approximately 5.03 GB) Hardware specifications: From 7347180440a38222ca428e64262aed0f14e9f69b Mon Sep 17 00:00:00 2001 From: Mendon Kissling <59585235+mendonk@users.noreply.github.com> Date: Tue, 28 Oct 2025 13:44:02 -0400 Subject: [PATCH 6/6] Apply suggestion from @aimurphy Co-authored-by: April I. Murphy <36110273+aimurphy@users.noreply.github.com> --- docs/docs/get-started/what-is-openrag.mdx | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/docs/get-started/what-is-openrag.mdx b/docs/docs/get-started/what-is-openrag.mdx index 6b6f71c8..129d2df9 100644 --- a/docs/docs/get-started/what-is-openrag.mdx +++ b/docs/docs/get-started/what-is-openrag.mdx @@ -120,5 +120,6 @@ Test results: 2025-09-24T23:19:44.866365Z /app/src/main.py:351 Langflow ingestion completed success_count=1070 error_count=12 total_files=1082 ``` -* Elapsed time: ~42 minutes 15 seconds (2,535 seconds) -* Throughput: ~2.4 documents/second \ No newline at end of file +Elapsed time: ~42 minutes 15 seconds (2,535 seconds) + +Throughput: ~2.4 documents/second \ No newline at end of file